© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155722
    Prev
    Next
    INDEX
    Explanations

    legally required phrasing or conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    language translation, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     נ
    0.53
     לא
    0.48
     הוא
    0.46
     ن
    0.44
    比如說
    0.44
     يعني
    0.44
    0
    0.43
     בא
    0.43
     よ
    0.41
    さんの
    0.41
    POSITIVE LOGITS
    imizde
    0.65
    kala
    0.52
    aliśmy
    0.51
    ⨔
    0.51
    imizin
    0.50
    ருங்க
    0.50
    र्ग
    0.49
    čun
    0.49
    र्मा
    0.48
    oja
    0.48
    Activations Density 0.000%

    No Known Activations